pip install modal
modal setup          # Opens browser login, writes token to ~/.modal.toml
# Verify:
modal run -q 'print("ok")'

Cost estimate (Modal):
  Model: [name] ([params], [precision])
  VRAM: ~[X]GB (weights + KV cache + overhead)
  GPU: [type] ([VRAM]GB, $[X]/sec = $[X]/hr, bandwidth [X] GB/s)
  Estimate: ~[N] min, ~$[X]

import modal

app = modal.App("experiment-name")
image = modal.Image.debian_slim(python_version="3.11").pip_install(
    "torch", "transformers", "accelerate", "datasets", "wandb"
)

# Mount local project code into the container
local_code = modal.Mount.from_local_dir(".", remote_path="/workspace")
# Persistent volume for checkpoints and results
volume = modal.Volume.from_name("experiment-results", create_if_missing=True)

@app.function(
    image=image,
    gpu="A100-80GB",          # Chosen based on Step 1 analysis
    mounts=[local_code],
    volumes={"/results": volume},
    timeout=3600 * 6,         # 6 hours max
    secrets=[modal.Secret.from_name("wandb-secret")],  # Optional
)
def train():
    import subprocess
    subprocess.run(
        ["python", "train.py", "--output_dir", "/results/run_001"],
        cwd="/workspace",
        check=True,
    )
    volume.commit()  # Persist results to volume

@app.local_entrypoint()
def main():
    train.remote()
    print("Training complete. Results saved to Modal volume 'experiment-results'.")

import modal

app = modal.App("inference-api")
image = modal.Image.debian_slim(python_version="3.11").pip_install(
    "torch", "transformers", "accelerate"
)

@app.cls(image=image, gpu="L40S")
@modal.concurrent(max_inputs=10)
class InferenceAPI:
    @modal.enter()
    def load_model(self):
        from transformers import AutoModelForCausalLM, AutoTokenizer
        self.tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B")
        self.model = AutoModelForCausalLM.from_pretrained(
            "meta-llama/Llama-3.2-1B", device_map="auto"
        )

    @modal.fastapi_endpoint(method="POST")
    def generate(self, request: dict):
        inputs = self.tokenizer(request.get("prompt", ""), return_tensors="pt").to("cuda")
        outputs = self.model.generate(**inputs, max_new_tokens=256)
        return {"text": self.tokenizer.decode(outputs[0], skip_special_tokens=True)}

import modal, subprocess

app = modal.App("vllm-server")
image = modal.Image.debian_slim(python_version="3.11").pip_install("vllm")
VOLUME = modal.Volume.from_name("model-cache", create_if_missing=True)
MODEL = "Qwen/Qwen3-4B"

@app.function(image=image, gpu="H100", volumes={"/models": VOLUME}, timeout=3600)
@modal.concurrent(max_inputs=100)
@modal.web_server(port=8000)
def serve():
    subprocess.Popen(["python", "-m", "vllm.entrypoints.openai.api_server",
                      "--model", MODEL, "--download-dir", "/models", "--port", "8000"])

@app.function(image=image, gpu="T4", timeout=600)
def process_item(item: dict) -> dict:
    # ... process one item ...
    return {"result": "processed"}

@app.local_entrypoint()
def main():
    results = list(process_item.map([{"id": i} for i in range(1000)]))

@app.function(
    image=image, gpu="A100-80GB", volumes={"/output": volume},
    timeout=3600 * 6, secrets=[modal.Secret.from_name("huggingface-secret")],
)
def train():
    # ... transformers + peft + trl training code ...
    trainer.save_model("/output/final")
    volume.commit()

@app.function(image=image, gpu="H100:4", volumes={"/output": volume}, timeout=3600 * 12)
def train_distributed():
    import subprocess
    subprocess.run(["accelerate", "launch", "--num_processes", "4",
                    "--mixed_precision", "bf16", "train.py"], check=True)

modal run launcher.py     # One-shot execution (most common for experiments)
modal deploy app.py       # Persistent service deployment

modal app list            # List running apps
modal app logs <app-name> # Stream logs

# Download results from volume after run completes
# Option A: In the launcher script, copy results to local mount before exit
# Option B: Use modal volume commands
modal volume ls experiment-results
modal volume get experiment-results /run_001/results.json ./results/

modal app stop <app-name>     # Stop a deployed service
modal volume rm <volume-name> # Delete a volume when done

modal run app.py          # Run once
modal deploy app.py       # Deploy persistent service
modal app logs <app>      # View logs
modal app list            # List apps
modal app stop <app>      # Stop
modal volume ls           # List volumes
modal volume get <vol> <remote> <local>  # Download from volume
modal secret create NAME KEY=VALUE       # Create secret

/run-experiment "train model"       <- detects gpu: modal, calls /serverless-modal
  -> /serverless-modal              <- analyzes task, generates launcher, runs
  -> Results returned locally or to Modal Volume
  -> No destroy step needed (auto scale-to-zero)

/serverless-modal                   <- standalone: any Modal GPU workload
/serverless-modal "deploy vLLM"     <- inference service deployment

## Modal
- gpu: modal                 # tells run-experiment to use Modal serverless
- modal_gpu: A100-80GB       # optional: override GPU selection (default: auto-select)
- modal_timeout: 21600       # optional: max seconds (default: 6 hours)
- modal_volume: my-results   # optional: named volume for results persistence